1 |
769 |
jeremybenn |
/* EncodingHelper.java -- Useful character encoding methods.
|
2 |
|
|
Copyright (C) 2005 Free Software Foundation, Inc.
|
3 |
|
|
|
4 |
|
|
This file is part of GNU Classpath.
|
5 |
|
|
|
6 |
|
|
GNU Classpath is free software; you can redistribute it and/or modify
|
7 |
|
|
it under the terms of the GNU General Public License as published by
|
8 |
|
|
the Free Software Foundation; either version 2, or (at your option)
|
9 |
|
|
any later version.
|
10 |
|
|
|
11 |
|
|
GNU Classpath is distributed in the hope that it will be useful, but
|
12 |
|
|
WITHOUT ANY WARRANTY; without even the implied warranty of
|
13 |
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
14 |
|
|
General Public License for more details.
|
15 |
|
|
|
16 |
|
|
You should have received a copy of the GNU General Public License
|
17 |
|
|
along with GNU Classpath; see the file COPYING. If not, write to the
|
18 |
|
|
Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
|
19 |
|
|
02110-1301 USA.
|
20 |
|
|
|
21 |
|
|
Linking this library statically or dynamically with other modules is
|
22 |
|
|
making a combined work based on this library. Thus, the terms and
|
23 |
|
|
conditions of the GNU General Public License cover the whole
|
24 |
|
|
combination.
|
25 |
|
|
|
26 |
|
|
As a special exception, the copyright holders of this library give you
|
27 |
|
|
permission to link this library with independent modules to produce an
|
28 |
|
|
executable, regardless of the license terms of these independent
|
29 |
|
|
modules, and to copy and distribute the resulting executable under
|
30 |
|
|
terms of your choice, provided that you also meet, for each linked
|
31 |
|
|
independent module, the terms and conditions of the license of that
|
32 |
|
|
module. An independent module is a module which is not derived from
|
33 |
|
|
or based on this library. If you modify this library, you may extend
|
34 |
|
|
this exception to your version of the library, but you are not
|
35 |
|
|
obligated to do so. If you do not wish to do so, delete this
|
36 |
|
|
exception statement from your version. */
|
37 |
|
|
|
38 |
|
|
|
39 |
|
|
package gnu.java.nio.charset;
|
40 |
|
|
|
41 |
|
|
import java.util.HashMap;
|
42 |
|
|
import java.nio.charset.IllegalCharsetNameException;
|
43 |
|
|
import java.nio.charset.UnsupportedCharsetException;
|
44 |
|
|
import java.nio.charset.Charset;
|
45 |
|
|
import java.io.UnsupportedEncodingException;
|
46 |
|
|
|
47 |
|
|
/**
|
48 |
|
|
* This class provides some useful utility methods
|
49 |
|
|
* for charset encoding for the java.lang and java.io methods.
|
50 |
|
|
*
|
51 |
|
|
* @author Sven de Marothy
|
52 |
|
|
*/
|
53 |
|
|
public class EncodingHelper
|
54 |
|
|
{
|
55 |
|
|
|
56 |
|
|
/**
|
57 |
|
|
* Contains the mapping from java.io canonical names
|
58 |
|
|
* to java.nio canonical names.
|
59 |
|
|
*/
|
60 |
|
|
private static final HashMap<String,String> canonicalNames;
|
61 |
|
|
|
62 |
|
|
static {
|
63 |
|
|
canonicalNames = new HashMap<String,String>();
|
64 |
|
|
canonicalNames.put("US-ASCII", "ASCII");
|
65 |
|
|
canonicalNames.put("windows-1250", "Cp1250");
|
66 |
|
|
canonicalNames.put("windows-1251", "Cp1251");
|
67 |
|
|
canonicalNames.put("windows-1252", "Cp1252");
|
68 |
|
|
canonicalNames.put("windows-1253", "Cp1253");
|
69 |
|
|
canonicalNames.put("windows-1254", "Cp1254");
|
70 |
|
|
canonicalNames.put("windows-1257", "Cp1257");
|
71 |
|
|
canonicalNames.put("ISO-8859-1", "ISO8859_1");
|
72 |
|
|
canonicalNames.put("ISO-8859-2", "ISO8859_2");
|
73 |
|
|
canonicalNames.put("ISO-8859-4", "ISO8859_4");
|
74 |
|
|
canonicalNames.put("ISO-8859-5", "ISO8859_5");
|
75 |
|
|
canonicalNames.put("ISO-8859-7", "ISO8859_7");
|
76 |
|
|
canonicalNames.put("ISO-8859-9", "ISO8859_9");
|
77 |
|
|
canonicalNames.put("ISO-8859-13", "ISO8859_13");
|
78 |
|
|
canonicalNames.put("ISO-8859-15", "ISO8859_15");
|
79 |
|
|
canonicalNames.put("KOI8-R", "KOI8_R");
|
80 |
|
|
canonicalNames.put("UTF-8", "UTF8");
|
81 |
|
|
canonicalNames.put("UTF-16BE", "UnicodeBigUnmarked");
|
82 |
|
|
canonicalNames.put("UTF-16LE", "UnicodeLittleUnmarked");
|
83 |
|
|
canonicalNames.put("windows-1255", "Cp1255");
|
84 |
|
|
canonicalNames.put("windows-1256", "Cp1256");
|
85 |
|
|
canonicalNames.put("windows-1258", "Cp1258");
|
86 |
|
|
canonicalNames.put("ISO-8859-3", "ISO8859_3");
|
87 |
|
|
canonicalNames.put("ISO-8859-6", "ISO8859_6");
|
88 |
|
|
canonicalNames.put("ISO-8859-8", "ISO8859_8");
|
89 |
|
|
}
|
90 |
|
|
|
91 |
|
|
/**
|
92 |
|
|
* Returns the name of the default encoding,
|
93 |
|
|
* falls back on defaults to Latin-1 if there's a problem.
|
94 |
|
|
*/
|
95 |
|
|
public static String getDefaultEncoding()
|
96 |
|
|
{
|
97 |
|
|
try
|
98 |
|
|
{
|
99 |
|
|
return System.getProperty("file.encoding");
|
100 |
|
|
} catch(SecurityException e) {
|
101 |
|
|
} catch(IllegalArgumentException e) {
|
102 |
|
|
}
|
103 |
|
|
// XXX - Throw an error here? For now, default to the 'safe' encoding.
|
104 |
|
|
return "8859_1";
|
105 |
|
|
}
|
106 |
|
|
|
107 |
|
|
/**
|
108 |
|
|
* Returns the java.io canonical name of a charset given with the
|
109 |
|
|
* java.nio canonical name. If the charset does not have a java.io
|
110 |
|
|
* canonical name, the input string is returned.
|
111 |
|
|
*/
|
112 |
|
|
public static String getOldCanonical(String newCanonical)
|
113 |
|
|
{
|
114 |
|
|
String oldCanonical = (String) canonicalNames.get(newCanonical);
|
115 |
|
|
return (oldCanonical != null)?oldCanonical : newCanonical;
|
116 |
|
|
}
|
117 |
|
|
|
118 |
|
|
public static boolean isISOLatin1(String s)
|
119 |
|
|
{
|
120 |
|
|
if(s.equals("ISO-8859-1") ||
|
121 |
|
|
s.equals("8859_1") ||
|
122 |
|
|
s.equals("ISO_8859-1") ||
|
123 |
|
|
s.equals("latin1") ||
|
124 |
|
|
s.equals("ISO8859_1") ||
|
125 |
|
|
s.equals("ISO_8859_1"))
|
126 |
|
|
return true;
|
127 |
|
|
return false;
|
128 |
|
|
}
|
129 |
|
|
|
130 |
|
|
/**
|
131 |
|
|
* Gets a charset, throwing the java.io exception and not
|
132 |
|
|
* the java.nio exception if an error occurs.
|
133 |
|
|
*/
|
134 |
|
|
public static Charset getCharset(String name)
|
135 |
|
|
throws UnsupportedEncodingException
|
136 |
|
|
{
|
137 |
|
|
try
|
138 |
|
|
{
|
139 |
|
|
return Charset.forName(name);
|
140 |
|
|
}
|
141 |
|
|
catch(IllegalCharsetNameException e)
|
142 |
|
|
{
|
143 |
|
|
throw new UnsupportedEncodingException("Charset "+name+" not found.");
|
144 |
|
|
}
|
145 |
|
|
catch(UnsupportedCharsetException e)
|
146 |
|
|
{
|
147 |
|
|
throw new UnsupportedEncodingException("Charset "+name+" not found.");
|
148 |
|
|
}
|
149 |
|
|
}
|
150 |
|
|
|
151 |
|
|
/**
|
152 |
|
|
* Returns the default charset without throwing any exceptions. The default
|
153 |
|
|
* charset is UTF8.
|
154 |
|
|
*
|
155 |
|
|
* @return the default charset
|
156 |
|
|
*/
|
157 |
|
|
public static Charset getDefaultCharset()
|
158 |
|
|
{
|
159 |
|
|
return new UTF_8();
|
160 |
|
|
}
|
161 |
|
|
}
|